Sökning: "Sannolikhetsfördelning"

Visar resultat 1 - 5 av 30 uppsatser innehållade ordet Sannolikhetsfördelning.

  1. 1. The deductibles impact on the risk premium

    Master-uppsats, Umeå universitet/Institutionen för matematik och matematisk statistik

    Författare :Ludvig Bergman; [2023]
    Nyckelord :deductible; insurance mathematics; non-life insurance pricing; Försäkringsmatematik; självrisk; självrisker;

    Sammanfattning : The aim of this master thesis is to derive methods that assesses the impact the deductiblehas on the risk premium of an insurance contract. The additive structure of a deductiblenecessitates approaches beyond treating it as a regular covariate in a generalized linearmodel for predicting the risk premium. LÄS MER

  3. 2. Credit Exposure Modelling Using Differential Machine Learning

    Master-uppsats, Lunds universitet/Matematisk statistik

    Författare :Måns Karp; Samuel Wagner; [2023]
    Nyckelord :Counterparty credit risk; Differential machine learning; Exposure modelling; Heston model; Option pricing; Mathematics and Statistics;

    Sammanfattning : Exposure modelling is a critical aspect of managing counterparty credit risk, and banks worldwide invest significant time and computational resources in this task. One approach to modelling exposure involves pricing trades with a counterparty in numerous potential future market scenarios. LÄS MER

  4. 3. Exploring Column Update Elimination Optimization for Spike-Timing-Dependent Plasticity Learning Rule

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Ojasvi Singh; [2022]
    Nyckelord :Spike-Timing Dependent Plasticity; neuromorphic computing; Hebbian Learning; Spiking Neural Networks; memory optimization.; Spike-Timing Beroende Plasticitet; neuromorfisk beräkning; Hebbiansk inlärning; Spiking Neural Networks; Minnes optimering;

    Sammanfattning : Hebbian learning based neural network learning rules when implemented on hardware, store their synaptic weights in the form of a two-dimensional matrix. The storage of synaptic weights demands large memory bandwidth and storage. LÄS MER

  5. 4. Generating synthetic golf courses with deep learning : Investigation into the uses and limitations of generative deep learning

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Carl Lundqvist; [2022]
    Nyckelord :Generative adverserial networks; generative models; golf; terrain generation; GAN; Generativa adversiella nätverk; generativa modeller; golf; genererad terräng; GAN;

    Sammanfattning : The power of generative deep learning has increased very quickly in the past ten years and modern models are now able to generate human faces that are indistinguishable from real ones. This thesis project will investigate the uses and limitations of this technology by attempting to generate very specific data, images of golf holes. LÄS MER

  7. 5. Analyzing the Negative Log-Likelihood Loss in Generative Modeling

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Aleix Espuña I Fontcuberta; [2022]
    Nyckelord :Generative modeling; Normalizing flows; Generative Adversarial Networks; MaximumLikelihood Estimation; Real Non-Volume Preserving flow; Fréchet Inception Distance; Misspecification; Generativa metoder; Normalizing flows; Generative adversarial networks; Maximum likelihood-metoden; Real non-volume preserving flow; Fréchet inception distance; felspecificerade modeller;

    Sammanfattning : Maximum-Likelihood Estimation (MLE) is a classic model-fitting method from probability theory. However, it has been argued repeatedly that MLE is inappropriate for synthesis applications, since its priorities are at odds with important principles of human perception, and that, e.g. LÄS MER